In the early stage of drug development, the rapid and accurate evaluation of chemical toxicity is of great significance for improving efficiency. In recent years, a great number of excellent computational models have been developed for chemical toxicity prediction. However, these computational models tend to be "black box", which bring about very poor interpretability and cannot provide effective suggestions for the optimization of lead compounds with toxicity. In this research, we focused on the identification and collection of structural alerts (SAs) responsible for a series of important toxic endpoint. Then, we carried out effective storage of these structural alerts, and developed programs to realize online prediction service. The structural alert-based expert system for drug toxicity prediction was developed. With the help of structural alerts, people can quickly evaluate whether the target compounds are toxic. The specific structural fragments that lead to the chemical toxicity will be intuitively shown to provide valuable reference for the modification of the structures.
Due to data privacy issues, the formula of structural alert will not be shown. If any collaboration needed, please contact the program instructor Dr. Li: firstname.lastname@example.org